neural networks research group
areas
people
projects
demos
publications
software/data
Teaching an Agent Manually via Evaluative Reinforcement (TAMER)
Since 2008
The TAMER project seeks to create agents which can be effectively taught behaviors by lay people using positive and negative feedback signals (akin to "shaping" by reward and punishment in animal training).
http://web.media.mit.edu/~bradknox/TAMER.html
People
W. Bradley Knox
bradknox [at] mit edu
Peter Stone
pstone [at] cs utexas edu
Ian Fasel
ianfasel [at] cs utexas edu
Adam Setapen
asetapen [at] cs utexas edu
Demos
Teaching an Agent Manually via Evaluative Reinforcement (TAMER)
W. Bradley Knox and Peter Stone
2009
Publications
Learning Non-Myopically from Human-Generated Reward
W. Bradley Knox and Peter Stone
In
In Proceedings of the International Conference on Intelligent User Interfaces (IUI)
, March...
2013
How Humans Teach Agents: A New Experimental Perspective
W. Bradley Knox and Brian D. Glass and Bradley C. Love and W. Todd Maddox and Peter Stone
International Journal of Social Robotics
, 4:409-421, 2012. Springer Netherlands.
2012
Learning from feedback on actions past and intended
W. Bradley Knox and Cynthia Breazeal and Peter Stone
In
In Proceedings of 7th ACM/IEEE International Conference on Human-Robot Interaction, Late-Break...
2012
Learning from Human-Generated Reward
W. Bradley Knox
%RefShort%
2012
Reinforcement Learning from Human Reward: Discounting in Episodic Tasks
W. Bradley Knox and Peter Stone
In
In Proceedings of the 21st IEEE International Symposium on Robot and Human Interactive Communi...
2012
Reinforcement Learning with Human and MDP Reward
W. Bradley Knox and Peter Stone
In
Proceedings of the 11th International Conference on Autonomous Agents and Multiagent Systems (...
2012
Understanding Human Teaching Modalities in Reinforcement Learning Environments: A Preliminary Report
W. Bradley Knox and Peter Stone
In
IJCAI 2011 Workshop on Agents Learning Interactively from Human Teachers (ALIHT)
, July 201...
2011
Combining Manual Feedback with Subsequent MDP Reward Signals for Reinforcement Learning
W. Bradley Knox and Peter Stone
In
Proc. of 9th Int. Conf. on Autonomous Agents and Multiagent Systems (AAMAS 2010)
, May 2010...
2010
Design Principles for Creating Human-Shapable Agents
W. Bradley Knox and Ian Fasel and Peter Stone
In
AAAI Spring 2009 Symposium on Agents that Learn from Human Teachers
, March 2009.
2009
Interactively Shaping Agents via Human Reinforcement: The TAMER Framework
W. Bradley Knox and Peter Stone
In
The Fifth International Conference on Knowledge Capture
, September 2009.
2009
Related Areas
Advice-taking Learners
Social Agents
Supervised Learning
Transfer Learning
Reinforcement Learning
Robotics
Cognitive Science